AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Home/
RAG / Knowledge Base/
deep-research
deep-research logo

deep-research

Active·★ 4.7k·MIT·Updated 2026-06-18

Deep Research (by u14app) is an open-source web app that produces in-depth research reports in a few minutes. It combines a "thinking" model for planning and analysis with a faster "task" model for gathering and summarising, plus web search, and lets you refine the report at any stage and re-run research from that point.

It suits individuals who want a self-hosted alternative to commercial deep-research features with their own choice of models and search providers. It supports Gemini, OpenAI, Anthropic, DeepSeek, Grok, Mistral, Azure OpenAI, OpenRouter, Ollama and any OpenAI-compatible model, and search engines such as SearXNG, Tavily, Firecrawl, Exa, Bocha and Brave, so even models without built-in search can research the web. You can upload text, Office and PDF files as a local knowledge base, edit the final report in a WYSIWYM or Markdown editor, generate a knowledge graph, and keep a research history. Data is stored in your browser, and the project can also act as a research service through an SSE API or an MCP server.

Getting started: deploy to Vercel or Cloudflare with one click, or run it with Docker (`docker run -d --name deep-research -p 3333:3000 xiangfa/deep-research`), then add API keys for your model and search providers in the settings.

This write-up is based on the project's README and public repository data. We have not hand-tested the tool. Data as of 2026-10-24.

License
MIT
Latest release
v0.11.0 · 2026-02-10
Last commit
2026-06-18
Contributors
11
Forks
1,056
Open issues and PRs
42
First published
2025-02-22

Source: GitHub, npm and PyPI public APIs.

#AI Research#LLM#Privacy-focused#Web Search#Next.js#Web Browsing
$ Install
$ docker run -d --name deep-research -p 3333:3000 xiangfa/deep-research
↗ Visit site★ GitHub
01

Features

01Rapidly generates comprehensive research reports in minutes.
02Ensures privacy by processing and storing all data locally in the browser.
03Supports a wide range of mainstream large language models (LLMs).
04Integrates with various web search engines for enhanced information gathering.
05Allows uploading and processing local files to build a knowledge base.
02

Why choose it

+Fast reports with a two-model design that balances depth and speed.
+Very broad support for model providers and search engines, including self-hosted SearXNG and local Ollama.
+Editable reports, knowledge graphs, local knowledge base and research history.
+Easy deployment (Vercel, Cloudflare, Docker) and MIT licensed.
03

Trade-offs

!Report quality depends on the models and search provider you configure; check sources before relying on conclusions.
!Updates have slowed: our directory records the last update in June 2026.
!Data stored in the browser is convenient but easy to lose if you clear site data; export important reports.
04

Maintenance check

SlowingChecked: 2026-10-27
Last commit
2026-06-18
Commits, last 90 days
0
Releases, last 90 days
0
Latest release
v0.11.0 (2026-02-10)
Open issues
42
Recent issues with at least one comment
21/29
Commits per week, last 12 weeks
Commits per week, last 12 weeks: 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0

Oldest week on the left; the latest four weeks are orange. Source: GitHub commit activity.

Status rule: archived on GitHub = Archived; last commit within 90 days = Active; 91 to 365 days = Slowing; older = Stale. All figures come from the GitHub API on the date shown.

Most discussed open issues

  • #115 [Bug]: Error: Method Not Allowed29 comments · 2025-07-22
  • #91 [Bug]: 500 Internal Error and SyntaxError: Unexpected end of JSON input when using Server-Side Proxy (Searxng/Uni-API) in Docker Compose15 comments · 2025-06-10
  • #49 [Feature Request]: Improve Research Section Export and LLM Integration10 comments · 2025-05-02
  • #120 [Bug]: SSE - Unknown event: message / missing citations / premature end9 comments · 2025-07-29
  • #124 [Bug]: When using the API to study, the error "Invalid state: Controller is already closed" appears.6 comments · 2025-07-31

Issue titles are quoted from GitHub. Open the link to check whether a problem still applies to the version you use.

05

Compatibility

Gemini
Native Support
Verified via docs
OpenAI
Supported
Verified via docs
Ollama
Supported
Verified via docs
Vercel
Deployment Platform
Verified via docs
Docker
Containerized Deployment
Verified via docs
Searxng
Search Provider
Verified via docs
06

Quick start

1
$ docker run -d --name deep-research -p 3333:3000 xiangfa/deep-research
07

Use cases

↳Rapidly generate in-depth research reports for personal and professional use.
↳Serve as a deep research as a service (SaaS) platform via SSE API.
↳Integrate deep research functionality into other AI applications using MCP.
08

Alternatives

⚡Top VS:
VSICLR2025-Papers-with-Code★589→VSdeer-flow★84.5k→VSragflow★93.0k→VSGPT Researcher★30.3k→
ICLR2025-Papers-with-Code logo
ICLR2025-Papers-with-Code★ 589
历年ICLR论文和开源项目合集,包含ICLR2021、ICLR2022、ICLR2023、ICLR2024、ICLR2025.
VSCompare→
deer-flow logo
deer-flow★ 84.5k
DeerFlow is a community-driven Deep Research framework, combining language models with tools like web search, crawling, and Python execution, while contributing back to the open-source community.
VSCompare→
ragflow logo
ragflow★ 93.0k
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
VSCompare→
GPT Researcher logo
GPT Researcher★ 30.3k
An autonomous agent that conducts deep research on any data using any LLM provider, producing detailed reports with citations from web and local sources.
VSCompare→
MaxKB logo
MaxKB★ 23.1k
An open-source platform for building enterprise-grade agents. Powerful and easy to use.
VSCompare→
AgentGuide logo
AgentGuide★ 11.3k
https://adongwanai.github.io/AgentGuide | AI Agent开发指南 | LangGraph实战 | 高级RAG | 转行大模型 | 大模型面试 | 算法工程师 | 面试题库 | 强化学习|数据合成
VSCompare→
MiroThinker logo
MiroThinker★ 8.4k
MiroThinker is an open source deep research agent optimized for research and prediction. It achieves a 80.8% Avg@8 score on the challenging GAIA benchmark.
VSCompare→
AIGC-Interview-Book logo
AIGC-Interview-Book★ 5.1k
【三年面试五年模拟】AIGC算法工程师面试秘籍。涵盖AIGC、传统深度学习、自动驾驶、AI Agent、机器学习、计算机视觉、自然语言处理、强化学习、大数据挖掘、具身智能、元宇宙、AGI等AI行业面试笔试干货经验与核心知识。
VSCompare→
See all alternatives →

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Why choose it03Trade-offs04Maintenance check05Compatibility06Quick start07Use cases08Alternatives
u14app /
deep-research
↗

Self-hosted deep research app with any model or search engine

4.7k1.1kMIT
Last commit4mo ago
StatusActive
CategoryRAG / Knowledge Base
Contributors11
Latest releasev0.11.0
Links
Documentation↗Discussion↗Issues↗Releases↗
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.